ISIC CNN
Deep Neural Network trained for the classification of dermoscopic images into nine categories.
Developed by
License
Other
The software has been developed using Pytorch and is probably under the same BSD 3 clause licence
Main Characteristic
Deep Neural Network trained for the classification of dermoscopic images into nine categories. The network has been trained on the ISIC dataset: https://challenge2019.isic-archive.com/ (brief description below). The Deep NN used is a pre-trained ResNet fine tuned for this specific task.
Research areas
Explainable AI
Business Categories
Healthcare
Last updated
27.05.2021 - 09:10
Detailed Description
Hardware architecture: X64
Additional information: The goal for ISIC 2019 is to classify dermoscopic images among nine different diagnostic categories:
- MEL: Melanoma
- NV: Melanocytic nevus
- BCC: Basal cell carcinoma
- AK: Actinic keratosis
- BKL: Benign keratosis (solar lentigo / seborrheic keratosis / lichen planus-like keratosis)
- DF: Dermatofibroma
- VASC: Vascular lesion
- SCC: Squamous cell carcinoma
- UNK: None of the others / out-of-distribution (OOD)
Documents
Trustworthy AI
We followed the guidelines: (1) lawful - respecting all applicable laws and regulations (2) ethical - respecting ethical principles and values (3) robust - both from a technical perspective while taking into account its social environment.
GDPR Requirements
No impact.